eicu-gcs

eicu-gcs is a skill for Claude Code, Codex from hannesill/m4. It costs 0 tokens per session (1,126 once invoked), scanned A, a copy of mimic-apsiii-24h-raw, MIT.

A SQL query for calculating the Glasgow Coma Scale, a clinical score describing a patient's level of consciousness, during the first 24 hours of an intensive-care stay in the eICU database.

In plain words
What is it for?
Use it in ICU studies that need first-day consciousness scores from eICU data.
Why use it?
It turns nurse charting records into a consistent first-day minimum score instead of requiring researchers to assemble the score manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it in ICU studies that need first-day consciousness scores from eICU data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hannesill/m4/eicu-gcs
View source ↗ hannesill/m4
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hannesill/m4 --skill eicu-gcs
Clone the repo
git clone --depth 1 https://github.com/hannesill/m4

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eicu-gcs

README.md
[![agentmods](https://agentmods.dev/badge/skills/hannesill/m4/eicu-gcs/github.svg)](https://agentmods.dev/skills/hannesill/m4/eicu-gcs)
Your own site
<a href="https://agentmods.dev/skills/hannesill/m4/eicu-gcs"><img src="https://agentmods.dev/badge/skills/hannesill/m4/eicu-gcs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eicu-gcs

Your own site · 80×15
<a href="https://agentmods.dev/skills/hannesill/m4/eicu-gcs"><img src="https://agentmods.dev/badge/skills/hannesill/m4/eicu-gcs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01126
Opus 5 $0.00000 $0.00563
Sonnet 5 $0.00000 $0.00225
Haiku 4.5 $0.00000 $0.00113

Measured 9d ago against content hash 47e4d3af9e97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eicu-gcs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to mimic-apsiii-24h-raw — 991 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

benchmark/tasks/gcs/eicu-gcs/skills-rawsql/eicu-gcs/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reference SQL (matched-content control)

The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.

-- ------------------------------------------------------------------
-- Title: Glasgow Coma Scale (GCS) — first day minimum (eICU)
-- Matches eicu-code pivoted-gcs.sql logic, then aggregates to
-- minimum GCS in the first 24 hours per ICU stay.
-- ------------------------------------------------------------------

-- Reference:
--    Teasdale G, Jennett B. "Assessment of coma and impaired
--    consciousness. A practical scale." Lancet. 1974;2(7872):81-84.

-- Adapted from eicu-code pivoted-gcs.sql (BigQuery → DuckDB)

-- Step 1: Extract GCS components from nursecharting, matching
-- eicu-code filter logic exactly.
WITH nc AS (
    SELECT
        patientunitstayid,
        nursingchartoffset AS chartoffset,
        -- GCS Total from two label patterns
        MIN(CASE
            WHEN nursingchartcelltypevallabel = 'Glasgow coma score'
             AND nursingchartcelltypevalname = 'GCS Total'
             AND TRY_CAST(nursingchartvalue AS NUMERIC) IS NOT NULL
                THEN CAST(nursingchartvalue AS NUMERIC)
            WHEN nursingchartcelltypevallabel = 'Score (Glasgow Coma Scale)'
             AND nursingchartcelltypevalname = 'Value'
             AND TRY_CAST(nursingchartvalue AS NUMERIC) IS NOT NULL
                THEN CAST(nursingchartvalue AS NUMERIC)
            ELSE NULL
        END) AS gcs,
        -- Motor
        MIN(CASE
            WHEN nursingchartcelltypevallabel = 'Glasgow coma score'
             AND nursingchartcelltypevalname = 'Motor'
             AND TRY_CAST(nursingchartvalue AS NUMERIC) IS NOT NULL
                THEN CAST(nursingchartvalue AS NUMERIC)
            ELSE NULL
        END) AS gcsmotor,
        -- Verbal
        MIN(CASE
            WHEN nursingchartcelltypevallabel = 'Glasgow coma score'
             AND nursingchartcelltypevalname = 'Verbal'
             AND TRY_CAST(nursingchartvalue AS NUMERIC) IS NOT NULL
                THEN CAST(nursingchartvalue AS NUMERIC)
            ELSE NULL
        END) AS gcsverbal,
        -- Eyes
        MIN(CASE
            WHEN nursingchartcelltypevallabel = 'Glasgow coma score'
             AND nursingchartcelltypevalname = 'Eyes'
             AND TRY_CAST(nursingchartvalue AS NUMERIC) IS NOT NULL
                THEN CAST(nursingchartvalue AS NUMERIC)
            ELSE NULL
        END) AS gcseyes
    FROM eicu_crd.nursecharting
    WHERE nursingchartcelltypecat IN ('Scores', 'Other Vital Signs and Infusions')
    GROUP BY patientunitstayid, nursingchartoffset
)

-- Step 2: Validate GCS range (3-15), matching eicu-code
, ncproc AS (
    SELECT
        patientunitstayid,
        chartoffset,
        CASE WHEN gcs > 2 AND gcs < 16 THEN gcs ELSE NULL END AS gcs,
        gcsmotor,
        gcsverbal,
        gcseyes
    FROM nc
    WHERE gcs IS NOT NULL
       OR gcsmotor IS NOT NULL
       OR gcsverbal IS NOT NULL
       OR gcseyes IS NOT NULL
)

-- Step 3: First-day minimum — find the minimum GCS in first 24h
-- Window: -6h before to +24h after ICU admission (offset -360 to 1440)
, gcs_first_day AS (
    SELECT
        patientunitstayid,
        chartoffset,
        -- Use charted GCS total if available; else compute from components
        COALESCE(gcs, COALESCE(gcseyes, 4) + COALESCE(gcsmotor, 6) + COALESCE(gcsverbal, 5)) AS gcs_total,
        gcsmotor,
        gcsverbal,
        gcseyes,
        ROW_NUMBER() OVER (
            PARTITION BY patientunitstayid
            ORDER BY
                COALESCE(gcs, COALESCE(gcseyes, 4) + COALESCE(gcsmotor, 6) + COALESCE(gcsverbal, 5)),
                chartoffset
        ) AS rn
    FROM ncproc
    WHERE chartoffset >= -360
      AND chartoffset <= 1440
)

SELECT
    p.patientunitstayid,
    p.uniquepid,
    p.patienthealthsystemstayid,
    COALESCE(g.gcs_total, 15) AS gcs_min,
    COALESCE(g.gcsmotor, 6) AS gcs_motor,
    COALESCE(g.gcsverbal, 5) AS gcs_verbal,
    COALESCE(g.gcseyes, 4) AS gcs_eyes
FROM eicu_crd.patient p
LEFT JOIN gcs_first_day g
    ON p.patientunitstayid = g.patientunitstayid
    AND g.rn = 1
;

Read the full file on GitHub · 120 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 120 lines · 0 tokens per session scan A 47e4d3af9e97

Subscribe to this mod's changes

eicu-gcs is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,126 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mimic-apsiii-24h-raw, differing in 991 lines, and is treated as a copy.

Related

Other skills, from other repositories

arbor-agent-orchestrator

Top-level controller for recreating the open-source AutoResearch workflow as a suite of skills. Use when the user asks to run, emulate, extract, validate, or refine Arbor/AutoResearch behavior, especially when a coordinator must load phase skills for setup, ideation, executors, merge evaluation, novelty search…

RUC-NLPIR/Arbor · 77 tokens

cqrs-implementation

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

wshobson/agents · 35 tokens

projection-patterns

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

wshobson/agents · 36 tokens

migration-review

Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.

rohitg00/ai-engineering-from-scratch · 35 tokens

azure-resource-manager-postgresql-dotnet

Azure PostgreSQL Flexible Server SDK for .NET. Database management for PostgreSQL Flexible Server deployments. Use for creating servers, databases, firewall rules, configurations, backups, and high availability. Triggers: "PostgreSQL", "PostgreSqlFlexibleServer", "PostgreSQL Flexible Server", "Azure Database for…

microsoft/skills · 97 tokens

azure-data-tables-java

Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.

microsoft/skills · 47 tokens